MLLab Manual
MLLab Manual
1. Develop a program to create histograms for all numerical features and analyze the distribution of
each feature. Generate box plots for all numerical features and identify any outliers. Use California
Housing dataset.
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_california_housing
# Plot histograms
plt.figure(figsize=(15, 10))
for i, feature in enumerate(numerical_features):
plt.subplot(3, 3, i + 1)
sns.histplot(housing_df[feature], kde=True, bins=30, color='blue')
plt.title(f'Distribution of {feature}')
plt.tight_layout()
plt.show()
OUTPUT:
2. Develop a program to Compute the correlation matrix to understand the relationships between pairs
of features. Visualize the correlation matrix using a heatmap to know which variables have strong
positive/negative correlations. Create a pair plot to visualize pairwise relationships between features.
Use California Housing dataset.
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_california_housing
import numpy as np
import pandas as pd
from sklearn.datasets import load_iris
from sklearn.decomposition import PCA
import matplotlib.pyplot as plt
import pandas as pd
def find_s_algorithm(file_path):
data = pd.read_csv(file_path)
print("Training data:")
print(data)
attributes = data.columns[:-1]
class_label = data.columns[-1]
return hypothesis
file_path = 'training_data.csv'
hypothesis = find_s_algorithm(file_path)
print("\nThe final hypothesis is:", hypothesis)
OUTPUT:
5. Develop a program to implement k-Nearest Neighbour algorithm to classify the randomly generated
a) Label the first 50 points {x1,……,x50} as follows: if (xi ≤ 0.5), then xi ∊ Class1, else xi ∊
100 values of x in the range of [0,1]. Perform the following based on dataset generated.
Class1
b) Classify the remaining points, x51,……,x100 using KNN. Perform this for k=1,2,3,4,5,20,30
import numpy as np
import matplotlib.pyplot as plt
from collections import Counter
data = np.random.rand(100)
distances.sort(key=lambda x: x[0])
k_nearest_neighbors = distances[:k]
return Counter(k_nearest_labels).most_common(1)[0][0]
train_data = data[:50]
train_labels = labels
test_data = data[50:]
results = {}
for k in k_values:
print(f"Results for k = {k}:")
classified_labels = [knn_classifier(train_data, train_labels, test_point, k) for
test_point in test_data]
results[k] = classified_labels
print("Classification complete.\n")
for k in k_values:
classified_labels = results[k]
class1_points = [test_data[i] for i in range(len(test_data)) if
classified_labels[i] == "Class1"]
class2_points = [test_data[i] for i in range(len(test_data)) if
classified_labels[i] == "Class2"]
plt.figure(figsize=(10, 6))
plt.scatter(train_data, [0] * len(train_data), c=["blue" if label == "Class1" else
"red" for label in train_labels],
label="Training Data", marker="o")
plt.scatter(class1_points, [1] * len(class1_points), c="blue", label="Class1
(Test)", marker="x")
plt.scatter(class2_points, [1] * len(class2_points), c="red", label="Class2
(Test)", marker="x")
OUTPUT:
6. Implement the non-parametric Locally Weighted Regression algorithm in order to fit data points.
Select appropriate data set for your experiment and draw graphs.
import numpy as np
import matplotlib.pyplot as plt
np.random.seed(42)
X = np.linspace(0, 2 * np.pi, 100)
y = np.sin(X) + 0.1 * np.random.randn(100)
X_bias = np.c_[np.ones(X.shape), X]
plt.figure(figsize=(10, 6))
plt.scatter(X, y, color='red', label='Training Data', alpha=0.7)
plt.plot(x_test, y_pred, color='blue', label=f'LWR Fit
(tau={tau})', linewidth=2)
plt.xlabel('X', fontsize=12)
plt.ylabel('y', fontsize=12)
plt.title('Locally Weighted Regression', fontsize=14)
plt.legend(fontsize=10)
plt.grid(alpha=0.3)
plt.show()
OUTPUT:
7. Develop a program to demonstrate the working of Linear Regression and Polynomial Regression.
Use Boston Housing Dataset for Linear Regression and Auto MPG Dataset (for vehicle fuel
efficiency prediction) for Polynomial Regression.
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures,
StandardScaler
from sklearn.pipeline import make_pipeline
from sklearn.metrics import mean_squared_error, r2_score
def linear_regression_california():
housing = fetch_california_housing(as_frame=True)
X = housing.data[["AveRooms"]]
y = housing.target
model = LinearRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
def polynomial_regression_auto_mpg():
url = "https://archive.ics.uci.edu/ml/machine-learning-
databases/auto-mpg/auto-mpg.data"
column_names = ["mpg", "cylinders", "displacement",
"horsepower", "weight", "acceleration", "model_year", "origin"]
data = pd.read_csv(url, sep='\s+', names=column_names,
na_values="?")
data = data.dropna()
X = data["displacement"].values.reshape(-1, 1)
y = data["mpg"].values
poly_model = make_pipeline(PolynomialFeatures(degree=2),
StandardScaler(), LinearRegression())
poly_model.fit(X_train, y_train)
y_pred = poly_model.predict(X_test)
if __name__ == "__main__":
print("Demonstrating Linear Regression and Polynomial
Regression\n")
linear_regression_california()
polynomial_regression_auto_mpg()
DATA SET:
Outlook,Temperature,Humidity,Windy,PlayTennis
Sunny,Hot,High,FALSE,No
Sunny,Hot,High,TRUE,No
Overcast,Hot,High,FALSE,Yes
Rain,Cold,High,FALSE,Yes
Rain,Cold,High,TRUE,No
Overcast,Hot,High,TRUE,Yes
Sunny,Hot,High,FALSE,No
OUTPUT:
8. Develop a program to demonstrate the working of the decision tree algorithm. Use Breast Cancer
Data set for building the decision tree and apply this knowledge to classify a new sample.
data = load_breast_cancer()
X = data.data
y = data.target
plt.figure(figsize=(12,8))
tree.plot_tree(clf, filled=True, feature_names=data.feature_names,
class_names=data.target_names)
plt.title("Decision Tree - Breast Cancer Dataset")
plt.show()
OUTPUT:
9. Develop a program to implement the Naive Bayesian classifier considering Olivetti Face Data set for
training. Compute the accuracy of the classifier, considering a few test data sets.
import numpy as np
from sklearn.datasets import fetch_olivetti_faces
from sklearn.model_selection import train_test_split,
cross_val_score
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score, classification_report,
confusion_matrix
import matplotlib.pyplot as plt
gnb = GaussianNB()
gnb.fit(X_train, y_train)
y_pred = gnb.predict(X_test)
print("\nClassification Report:")
print(classification_report(y_test, y_pred, zero_division=1))
print("\nConfusion Matrix:")
print(confusion_matrix(y_test, y_pred))
plt.show()
OUTPUT:
10. Develop a program to implement k-means clustering using Wisconsin Breast Cancer data set and
visualize the clustering result.
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.datasets import load_breast_cancer
from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.metrics import confusion_matrix, classification_report
data = load_breast_cancer()
X = data.data
y = data.target
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
print("Confusion Matrix:")
print(confusion_matrix(y, y_kmeans))
print("\nClassification Report:")
print(classification_report(y, y_kmeans))
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X_scaled)
plt.figure(figsize=(8, 6))
sns.scatterplot(data=df, x='PC1', y='PC2', hue='Cluster',
palette='Set1', s=100, edgecolor='black', alpha=0.7)
plt.title('K-Means Clustering of Breast Cancer Dataset')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend(title="Cluster")
plt.show()
plt.figure(figsize=(8, 6))
sns.scatterplot(data=df, x='PC1', y='PC2', hue='True Label',
palette='coolwarm', s=100, edgecolor='black', alpha=0.7)
plt.title('True Labels of Breast Cancer Dataset')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend(title="True Label")
plt.show()
plt.figure(figsize=(8, 6))
sns.scatterplot(data=df, x='PC1', y='PC2', hue='Cluster',
palette='Set1', s=100, edgecolor='black', alpha=0.7)
centers = pca.transform(kmeans.cluster_centers_)
plt.scatter(centers[:, 0], centers[:, 1], s=200, c='red',
marker='X', label='Centroids')
plt.title('K-Means Clustering with Centroids')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend(title="Cluster")
plt.show()
OUTPUT: